© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138895
    Prev
    Next
    INDEX
    Explanations

    reveals, applies, pinpoint complex concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    戽
    0.46
    ຂອງ
    0.44
    jom
    0.42
    rentices
    0.40
    ですが
    0.39
    といった
    0.39
    vertrag
    0.39
     होतो
    0.39
     Бет
    0.39
    àm
    0.38
    POSITIVE LOGITS
     explotación
    0.49
     biomedical
    0.48
    💔
    0.48
     arid
    0.47
     gerecht
    0.46
     formalism
    0.46
     ataxia
    0.45
     neurologic
    0.45
     nonradiative
    0.45
     airway
    0.44
    Activations Density 0.007%

    No Known Activations